From 8aeefbbfdd1c25b63bf0c7aa4b7bf56047d4a65a Mon Sep 17 00:00:00 2001
From: "dan@daramos.com" <dan@daramos.com>
Date: Thu, 1 Jan 2015 01:22:43 -0500
Subject: [PATCH] Reimplement a minor optimization in String::from_utf8_lossy
that avoids having to loop the slice from the begining.
---
src/libcollections/string.rs | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/src/libcollections/string.rs b/src/libcollections/string.rs
index f703ff99660..e3f0860d613 100644
--- a/src/libcollections/string.rs
+++ b/src/libcollections/string.rs
@@ -141,14 +141,18 @@ impl String {
/// ```
#[stable]
pub fn from_utf8_lossy<'a>(v: &'a [u8]) -> CowString<'a> {
+ let mut i = 0;
match str::from_utf8(v) {
Ok(s) => return Cow::Borrowed(s),
- Err(..) => {}
+ Err(e) => {
+ if let Utf8Error::InvalidByte(firstbad) = e {
+ i = firstbad;
+ }
+ }
}
static TAG_CONT_U8: u8 = 128u8;
static REPLACEMENT: &'static [u8] = b"\xEF\xBF\xBD"; // U+FFFD in UTF-8
- let mut i = 0;
let total = v.len();
fn unsafe_get(xs: &[u8], i: uint) -> u8 {
unsafe { *xs.get_unchecked(i) }
@@ -172,7 +176,7 @@ impl String {
// subseqidx is the index of the first byte of the subsequence we're looking at.
// It's used to copy a bunch of contiguous good codepoints at once instead of copying
// them one by one.
- let mut subseqidx = 0;
+ let mut subseqidx = i;
while i < total {
let i_ = i;